© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 11625
    Prev
    Next
    INDEX
    Explanations

    instances of structured data formatting or tagging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.91
    #+#
    -0.80
    AxisAlignment
    -0.76
    __':
    -0.74
    تقاوى
    -0.69
    __':
    -0.67
    IRQn
    -0.67
    abancı
    -0.67
    verifyException
    -0.66
    setVerticalGroup
    -0.66
    POSITIVE LOGITS
     storage
    0.69
     storing
    0.67
    Preferences
    0.63
     stored
    0.61
     store
    0.60
    storage
    0.59
     STORAGE
    0.57
     Storage
    0.57
    Storage
    0.57
     ini
    0.55
    Activations Density 0.195%

    No Known Activations